|   | 
Details
   web
Records
Author (up) Jorge L. Charco; Angel D. Sappa; Boris X. Vintimilla; Henry O. Velesaca
Title Transfer Learning from Synthetic Data in the Camera Pose Estimation Problem Type Conference Article
Year 2020 Publication The 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020); Valletta, Malta; 27-29 Febrero 2020 Abbreviated Journal
Volume 4 Issue Pages 498-505
Keywords Relative Camera Pose Estimation, Siamese Architecture, Synthetic Data, Deep Learning, Multi-View Environments, Extrinsic Camera Parameters.
Abstract This paper presents a novel Siamese network architecture, as a variant of Resnet-50, to estimate the relative camera pose on multi-view environments. In order to improve the performance of the proposed model

a transfer learning strategy, based on synthetic images obtained from a virtual-world, is considered. The

transfer learning consist of first training the network using pairs of images from the virtual-world scenario

considering different conditions (i.e., weather, illumination, objects, buildings, etc.); then, the learned weight

of the network are transferred to the real case, where images from real-world scenarios are considered. Experimental results and comparisons with the state of the art show both, improvements on the relative pose

estimation accuracy using the proposed model, as well as further improvements when the transfer learning

strategy (synthetic-world data – transfer learning – real-world data) is considered to tackle the limitation on

the training due to the reduced number of pairs of real-images on most of the public data sets.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-989758402-2 Medium
Area Expedition Conference
Notes Approved no
Call Number gtsi @ user @ Serial 120
Permanent link to this record
 

 
Author (up) Rafael E. Rivadeneira; Angel D. Sappa; Boris X. Vintimilla
Title Thermal Image Super-Resolution: a Novel Architecture and Dataset Type Conference Article
Year 2020 Publication The 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020); Valletta, Malta; 27-29 Febrero 2020 Abbreviated Journal
Volume 4 Issue Pages 111-119
Keywords Thermal images, Far Infrared, Dataset, Super-Resolution.
Abstract This paper proposes a novel CycleGAN architecture for thermal image super-resolution, together with a large

dataset consisting of thermal images at different resolutions. The dataset has been acquired using three thermal

cameras at different resolutions, which acquire images from the same scenario at the same time. The thermal

cameras are mounted in rig trying to minimize the baseline distance to make easier the registration problem.

The proposed architecture is based on ResNet6 as a Generator and PatchGAN as Discriminator. The novelty

on the proposed unsupervised super-resolution training (CycleGAN) is possible due to the existence of aforementioned thermal images—images of the same scenario with different resolutions. The proposed approach

is evaluated in the dataset and compared with classical bicubic interpolation. The dataset and the network are

available.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-989758402-2 Medium
Area Expedition Conference
Notes Approved no
Call Number gtsi @ user @ Serial 121
Permanent link to this record